From owner-freebsd-current@FreeBSD.ORG Fri Oct 27 02:06:43 2006 Return-Path: X-Original-To: current@freebsd.org Delivered-To: freebsd-current@FreeBSD.ORG Received: from localhost.my.domain (localhost [127.0.0.1]) by hub.freebsd.org (Postfix) with ESMTP id 9197216A47B; Fri, 27 Oct 2006 02:06:43 +0000 (UTC) (envelope-from davidxu@freebsd.org) From: David Xu To: John Birrell Date: Fri, 27 Oct 2006 10:06:38 +0800 User-Agent: KMail/1.8.2 References: <20061026213343.GA29160@what-creek.com> <200610270851.39444.davidxu@freebsd.org> <20061027005733.GA31389@what-creek.com> In-Reply-To: <20061027005733.GA31389@what-creek.com> MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Content-Disposition: inline Message-Id: <200610271006.38851.davidxu@freebsd.org> Cc: current@freebsd.org Subject: Re: HEADSUP: KSE about to become a kernel option X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 27 Oct 2006 02:06:43 -0000 On Friday 27 October 2006 08:57, John Birrell wrote: > On Fri, Oct 27, 2006 at 08:51:39AM +0800, David Xu wrote: > > By compiling kernel without KSE option, super-smack's select-key.smack > > with 10 clients on Athlon64 dual-core 3800+ breaks 31000 q/s, otherwise > > it can only get 29000 q/s. Mysql version is 5.0.24a, FreeBSD AMD64. > > So that must be the difference in context switch time? > > -- > John Birrell I assume that without KSE, the scheduler's code size is reduced, this saves I-CACHE and execution time. David Xu